Mercurial > public > mercurial-scm > hg-stable
view mercurial/dirs.c @ 26117:4dc5b51f38fe
revlog: change generaldelta delta parent heuristic
The old generaldelta heuristic was "if p1 (or p2) was closer than the last full text,
use it, otherwise use prev". This was problematic when a repo contained multiple
branches that were very different. If commits to branch A were pushed, and the
last full text was branch B, it would generate a fulltext. Then if branch B was
pushed, it would generate another fulltext. The problem is that the last
fulltext (and delta'ing against `prev` in general) has no correlation with the
contents of the incoming revision, and therefore will always have degenerate
cases.
According to the blame, that algorithm was chosen to minimize the chain length.
Since there is already code that protects against that (the delta-vs-fulltext
code), and since it has been improved since the original generaldelta algorithm
went in (2011), I believe the chain length criteria will still be preserved.
The new algorithm always diffs against p1 (or p2 if it's closer), unless the
resulting delta will fail the delta-vs-fulltext check, in which case we delta
against prev.
Some before and after stats on manifest.d size.
internal large repo
old heuristic - 2.0 GB
new heuristic - 1.2 GB
mozilla-central
old heuristic - 242 MB
new heuristic - 261 MB
The regression in mozilla central is due to the new heuristic choosing p2r as
the delta when it's closer to the tip. Switching the algorithm to always prefer
p1r brings the size back down (242 MB). This is result of the way in which
mozilla does merges and pushes, and the result could easily swing the other
direction in other repos (depending on if they merge X into Y or Y into X), but
will never be as degenerate as before.
I future patch will address the regression by introducing an optional, even more
aggressive delta heuristic which will knock the mozilla manifest size down
dramatically.
author | Durham Goode <durham@fb.com> |
---|---|
date | Sun, 30 Aug 2015 13:58:11 -0700 |
parents | fe3a72a3e7ca |
children | 63e1dca2d6a4 |
line wrap: on
line source
/* dirs.c - dynamic directory diddling for dirstates Copyright 2013 Facebook This software may be used and distributed according to the terms of the GNU General Public License, incorporated herein by reference. */ #define PY_SSIZE_T_CLEAN #include <Python.h> #include "util.h" /* * This is a multiset of directory names, built from the files that * appear in a dirstate or manifest. * * A few implementation notes: * * We modify Python integers for refcounting, but those integers are * never visible to Python code. * * We mutate strings in-place, but leave them immutable once they can * be seen by Python code. */ typedef struct { PyObject_HEAD PyObject *dict; } dirsObject; static inline Py_ssize_t _finddir(const char *path, Py_ssize_t pos) { while (pos != -1) { if (path[pos] == '/') break; pos -= 1; } return pos; } static int _addpath(PyObject *dirs, PyObject *path) { const char *cpath = PyString_AS_STRING(path); Py_ssize_t pos = PyString_GET_SIZE(path); PyObject *key = NULL; int ret = -1; while ((pos = _finddir(cpath, pos - 1)) != -1) { PyObject *val; /* It's likely that every prefix already has an entry in our dict. Try to avoid allocating and deallocating a string for each prefix we check. */ if (key != NULL) ((PyStringObject *)key)->ob_shash = -1; else { /* Force Python to not reuse a small shared string. */ key = PyString_FromStringAndSize(cpath, pos < 2 ? 2 : pos); if (key == NULL) goto bail; } PyString_GET_SIZE(key) = pos; PyString_AS_STRING(key)[pos] = '\0'; val = PyDict_GetItem(dirs, key); if (val != NULL) { PyInt_AS_LONG(val) += 1; break; } /* Force Python to not reuse a small shared int. */ val = PyInt_FromLong(0x1eadbeef); if (val == NULL) goto bail; PyInt_AS_LONG(val) = 1; ret = PyDict_SetItem(dirs, key, val); Py_DECREF(val); if (ret == -1) goto bail; Py_CLEAR(key); } ret = 0; bail: Py_XDECREF(key); return ret; } static int _delpath(PyObject *dirs, PyObject *path) { char *cpath = PyString_AS_STRING(path); Py_ssize_t pos = PyString_GET_SIZE(path); PyObject *key = NULL; int ret = -1; while ((pos = _finddir(cpath, pos - 1)) != -1) { PyObject *val; key = PyString_FromStringAndSize(cpath, pos); if (key == NULL) goto bail; val = PyDict_GetItem(dirs, key); if (val == NULL) { PyErr_SetString(PyExc_ValueError, "expected a value, found none"); goto bail; } if (--PyInt_AS_LONG(val) <= 0) { if (PyDict_DelItem(dirs, key) == -1) goto bail; } else break; Py_CLEAR(key); } ret = 0; bail: Py_XDECREF(key); return ret; } static int dirs_fromdict(PyObject *dirs, PyObject *source, char skipchar) { PyObject *key, *value; Py_ssize_t pos = 0; while (PyDict_Next(source, &pos, &key, &value)) { if (!PyString_Check(key)) { PyErr_SetString(PyExc_TypeError, "expected string key"); return -1; } if (skipchar) { if (!dirstate_tuple_check(value)) { PyErr_SetString(PyExc_TypeError, "expected a dirstate tuple"); return -1; } if (((dirstateTupleObject *)value)->state == skipchar) continue; } if (_addpath(dirs, key) == -1) return -1; } return 0; } static int dirs_fromiter(PyObject *dirs, PyObject *source) { PyObject *iter, *item = NULL; int ret; iter = PyObject_GetIter(source); if (iter == NULL) return -1; while ((item = PyIter_Next(iter)) != NULL) { if (!PyString_Check(item)) { PyErr_SetString(PyExc_TypeError, "expected string"); break; } if (_addpath(dirs, item) == -1) break; Py_CLEAR(item); } ret = PyErr_Occurred() ? -1 : 0; Py_DECREF(iter); Py_XDECREF(item); return ret; } /* * Calculate a refcounted set of directory names for the files in a * dirstate. */ static int dirs_init(dirsObject *self, PyObject *args) { PyObject *dirs = NULL, *source = NULL; char skipchar = 0; int ret = -1; self->dict = NULL; if (!PyArg_ParseTuple(args, "|Oc:__init__", &source, &skipchar)) return -1; dirs = PyDict_New(); if (dirs == NULL) return -1; if (source == NULL) ret = 0; else if (PyDict_Check(source)) ret = dirs_fromdict(dirs, source, skipchar); else if (skipchar) PyErr_SetString(PyExc_ValueError, "skip character is only supported " "with a dict source"); else ret = dirs_fromiter(dirs, source); if (ret == -1) Py_XDECREF(dirs); else self->dict = dirs; return ret; } PyObject *dirs_addpath(dirsObject *self, PyObject *args) { PyObject *path; if (!PyArg_ParseTuple(args, "O!:addpath", &PyString_Type, &path)) return NULL; if (_addpath(self->dict, path) == -1) return NULL; Py_RETURN_NONE; } static PyObject *dirs_delpath(dirsObject *self, PyObject *args) { PyObject *path; if (!PyArg_ParseTuple(args, "O!:delpath", &PyString_Type, &path)) return NULL; if (_delpath(self->dict, path) == -1) return NULL; Py_RETURN_NONE; } static int dirs_contains(dirsObject *self, PyObject *value) { return PyString_Check(value) ? PyDict_Contains(self->dict, value) : 0; } static void dirs_dealloc(dirsObject *self) { Py_XDECREF(self->dict); PyObject_Del(self); } static PyObject *dirs_iter(dirsObject *self) { return PyObject_GetIter(self->dict); } static PySequenceMethods dirs_sequence_methods; static PyMethodDef dirs_methods[] = { {"addpath", (PyCFunction)dirs_addpath, METH_VARARGS, "add a path"}, {"delpath", (PyCFunction)dirs_delpath, METH_VARARGS, "remove a path"}, {NULL} /* Sentinel */ }; static PyTypeObject dirsType = { PyObject_HEAD_INIT(NULL) }; void dirs_module_init(PyObject *mod) { dirs_sequence_methods.sq_contains = (objobjproc)dirs_contains; dirsType.tp_name = "parsers.dirs"; dirsType.tp_new = PyType_GenericNew; dirsType.tp_basicsize = sizeof(dirsObject); dirsType.tp_dealloc = (destructor)dirs_dealloc; dirsType.tp_as_sequence = &dirs_sequence_methods; dirsType.tp_flags = Py_TPFLAGS_DEFAULT; dirsType.tp_doc = "dirs"; dirsType.tp_iter = (getiterfunc)dirs_iter; dirsType.tp_methods = dirs_methods; dirsType.tp_init = (initproc)dirs_init; if (PyType_Ready(&dirsType) < 0) return; Py_INCREF(&dirsType); PyModule_AddObject(mod, "dirs", (PyObject *)&dirsType); }